相关论文: Investigating Concept Alignment Using Implausible …

Deep Learning has already been successfully applied to analyze industrial sensor data in a variety of relevant use cases. However, the opaque nature of many well-performing methods poses a major obstacle for real-world deployment.…

Modern AI models contain much of human knowledge, yet understanding of their internal representation of this knowledge remains elusive. Characterizing the structure and properties of this representation will lead to improvements in model…

Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact,…

With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching or even exceeding the human level on an increasing number of complex tasks. Impressive examples of this…

Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of…

Do AI systems truly understand human concepts or merely mimic surface patterns? We investigate this through chess, where human creativity meets precise strategic concepts. Analyzing a 270M-parameter transformer that achieves…

High-level reasoning can be defined as the capability to generalize over knowledge acquired via experience, and to exhibit robust behavior in novel situations. Such form of reasoning is a basic skill in humans, who seamlessly use it in a…

This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and…

We define and study the problem of modular concept learning, that is, learning a concept that is a cross product of component concepts. If an element's membership in a concept depends solely on it's membership in the components, learning…

Humans leverage compositionality to efficiently learn new concepts, understanding how familiar parts can combine together to form novel objects. In contrast, popular computer vision models struggle to make the same types of inferences,…

An unsupervised shape analysis is proposed to learn concepts reflecting shape commonalities. Our approach is two-fold: i) a spatial topology analysis of point cloud segment constellations within objects is used in which constellations are…

Visual object recognition -- the behavioral ability to rapidly and accurately categorize many visually encountered objects -- is core to primate cognition. This behavioral capability is algorithmically impressive because of the myriad…

From its inception, AI has had a rather ambivalent relationship with humans -- swinging between their augmentation and replacement. Now, as AI technologies enter our everyday lives at an ever increasing pace, there is a greater need for AI…

As artificial intelligence systems become increasingly integrated into daily life, the field of explainability has gained significant attention. This trend is particularly driven by the complexity of modern AI models and their…

Evaluating explanations of image classifiers regarding ground truth, e.g. segmentation masks defined by human perception, primarily evaluates the quality of the models under consideration rather than the explanation methods themselves.…

Neural network models are widely used in a variety of domains, often as black-box solutions, since they are not directly interpretable for humans. The field of explainable artificial intelligence aims at developing explanation methods to…

AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when…

Large Language Models (LLMs) are recruited in applications that span from clinical assistance and legal support to question answering and education. Their success in specialized tasks has led to the claim that they possess human-like…

Interactive Artificial Intelligence (AI) agents are becoming increasingly prevalent in society. However, application of such systems without understanding them can be problematic. Black-box AI systems can lead to liability and…

As semi-autonomous vehicles (AVs) become prevalent, drivers must collaborate with AI systems whose decision-making processes remain opaque. This study examines how drivers of AVs develop folk theories to interpret algorithmic behavior that…